summit
Optimising chemical reactions using machine learning
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
✓DOI references
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: wiley.com -
✓Committers with academic emails
3 of 11 committers (27.3%) from academic institutions -
✓Institutional organization owner
Organization sustainable-processes has institutional domain (www.ceb.cam.ac.uk) -
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (16.0%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Optimising chemical reactions using machine learning
Basic Info
- Host: GitHub
- Owner: sustainable-processes
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Homepage: https://gosummit.readthedocs.io/en/latest/
- Size: 47.4 MB
Statistics
- Stars: 133
- Watchers: 6
- Forks: 29
- Open Issues: 12
- Releases: 17
Topics
Metadata Files
README.md
Summit
Summit is a set of tools for optimising chemical processes. We’ve started by targeting reactions. Go through a tutorial here!
What is Summit?
Currently, reaction optimisation in the fine chemicals industry is done by intuition or design of experiments. Both scale poorly with the complexity of the problem.
Summit uses recent advances in machine learning to make the process of reaction optimisation faster. Essentially, it applies algorithms that learn which conditions (e.g., temperature, stoichiometry, etc.) are important to maximising one or more objectives (e.g., yield, enantiomeric excess). This is achieved through an iterative cycle.
Summit has two key features:
- Strategies: Optimisation algorithms designed to find the best conditions with the least number of iterations. Summit has eight strategies implemented.
- Benchmarks: Simulations of chemical reactions that can be used to test strategies. We have both mechanistic and data-driven benchmarks.
To get started, see the Quick Start below or follow our tutorial.
Installation
To install summit, use the following command:
pip install summit
News
- Denali (0.8) is out! Read more about the release here.
- Kobi (@marcosfelt) gave a tutorial on Summit at the online Autonomous Discovery Symposium on Wednesday 21 April 2021. The tutorial can be found here.
Quick Start
Below, we show how to use the Nelder-Mead strategy to optimise a benchmark representing a nucleophlic aromatic substitution (SnAr) reaction.
```python
Import summit
from summit.benchmarks import SnarBenchmark from summit.strategies import SOBO, MultitoSingleObjective from summit.run import Runner
Instantiate the benchmark
exp = SnarBenchmark()
Since the Snar benchmark has two objectives and Nelder-Mead is single objective, we need a multi-to-single objective transform
transform = MultitoSingleObjective( exp.domain, expression="-sty/1e4+e_factor/100", maximize=False )
Set up the strategy, passing in the optimisation domain and transform
nm = SOBO(exp.domain, transform=transform)
Use the runner to run closed loop experiments
r = Runner( strategy=nm, experiment=exp,max_iterations=50 ) r.run()
Make a pareto plot comparing both objectives
r.experiment.pareto_plot() ```
Documentation
The documentation for summit can be found here.
Issues?
Submit an issue or send an email to kcmf2@cam.ac.uk.
Citing
If you find this project useful, we encourage you to
- Star this repository :star:
- Cite our paper.
@article{Felton2021, author = "Kobi Felton and Jan Rittig and Alexei Lapkin", title = "{Summit: Benchmarking Machine Learning Methods for Reaction Optimisation}", year = "2021", month = "2", url = "https://chemistry-europe.onlinelibrary.wiley.com/doi/full/10.1002/cmtd.202000051", journal = "Chemistry Methods" }
Owner
- Name: Sustainable Reaction Engineering Group
- Login: sustainable-processes
- Kind: organization
- Email: aal35@cam.ac.uk
- Location: Cambridge, UK
- Website: https://www.ceb.cam.ac.uk/research/groups/rg-sre
- Repositories: 34
- Profile: https://github.com/sustainable-processes
Software developed by the Sustainable Reaction Engineering group at the University of Cambridge
GitHub Events
Total
- Issues event: 2
- Watch event: 10
- Issue comment event: 15
- Pull request event: 1
- Fork event: 5
Last Year
- Issues event: 2
- Watch event: 10
- Issue comment event: 15
- Pull request event: 1
- Fork event: 5
Committers
Last synced: about 2 years ago
Top Committers
| Name | Commits | |
|---|---|---|
| marcosfelt | k****n@n****u | 111 |
| Kobi Felton | k****f@g****m | 87 |
| Kobi Felton | k****2@c****k | 69 |
| dependabot[bot] | 4****] | 12 |
| Jan Rittig | 6****t | 9 |
| Ilario Gelmetti | i****e@g****m | 2 |
| simonsung06 | 6****6 | 2 |
| Jeremy Sadler | 5****r | 2 |
| Daniel Wigh | 5****h | 1 |
| sweep-ai[bot] | 1****] | 1 |
| Kobi Felton | k****2@c****k | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 40
- Total pull requests: 85
- Average time to close issues: 5 months
- Average time to close pull requests: 7 days
- Total issue authors: 18
- Total pull request authors: 6
- Average comments per issue: 1.63
- Average comments per pull request: 0.54
- Merged pull requests: 61
- Bot issues: 0
- Bot pull requests: 27
Past Year
- Issues: 2
- Pull requests: 3
- Average time to close issues: N/A
- Average time to close pull requests: 2 days
- Issue authors: 2
- Pull request authors: 3
- Average comments per issue: 0.5
- Average comments per pull request: 5.67
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 1
Top Authors
Issue Authors
- marcosfelt (14)
- ilario (7)
- konkouz (3)
- Mishal-Benz (2)
- zjyz17 (1)
- RoryGeeson (1)
- gilbertblanson (1)
- dswigh (1)
- TedOiler (1)
- jb2197 (1)
- Yujikaiya (1)
- jcgsville (1)
- TSAndrews (1)
- zhangkaihua88 (1)
- njoseGIT (1)
Pull Request Authors
- marcosfelt (53)
- dependabot[bot] (24)
- ilario (5)
- sweep-ai[bot] (4)
- lolosssss (2)
- simonsung06 (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 205 last-month
- Total dependent packages: 0
- Total dependent repositories: 3
- Total versions: 14
- Total maintainers: 2
pypi.org: summit
Tools for optimizing chemical processes
- Homepage: https://github.com/sustainable-processes/summit
- Documentation: https://summit.readthedocs.io/
- License: MIT
-
Latest release: 0.8.9
published about 3 years ago
Rankings
Maintainers (2)
Dependencies
- 198 dependencies
- black ^20.8b1 develop
- ipdb 0.13.4 develop
- rope ^0.17.0 develop
- GPy ^1.9
- SQSnobFit ^0.4.3
- botorch ^0.5.0
- cython ^0.29.21
- entmoot ^0.1.4
- fastprogress ^0.2.3
- gpyopt ^1.2.6
- gpytorch ^1.5.0
- hiplot ^0.1.12
- jinja2 <3.1.0
- llvmlite ^0.38.0
- matplotlib ^3.2.2
- nbsphinx ^0.8.5
- neptune-client ^0.4.115
- numba ^0.55.0
- numpy ^1.21.0
- pandas ^1.1.0
- paramiko ^2.7.1
- pymoo ^0.4.1
- pyrecorder ^0.1.8
- pyrff ^2.0.1
- pytest ^6.2.5
- python ^3.8, <3.10
- scikit-learn ^1.0
- scipy >=1.8.0
- skorch ^0.9.0
- sphinx ^3.2.1
- sphinx-reredirects ^0.0.0
- sphinx-rtd-theme ^0.5.0
- streamlit ^0.67.1
- torch ^1.4.0
- xlrd ^1.2.0
- Gr1N/setup-poetry v7 composite
- actions/checkout v2 composite
- actions/download-artifact v3 composite
- actions/setup-python v2 composite
- actions/upload-artifact v3 composite
- python 3.7 build